# Cards Against AI: Predicting Humor in a Fill-in-the-blank Party Game

arXiv: https://arxiv.org/abs/2210.13016 · HTML: https://mlsanity.com/paper/2210.13016/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 4 of its 31 references that are in the map.
- First posted on arXiv 24 Oct 2022.

## Builds on (most cited first, 4 of 4)

- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [MiniLMv2: Multi-Head Self-Attention Relation Distillation for Compressing Pretrained Transformers](https://mlsanity.com/paper/2012.15828/) (2020)
- ["Judge me by my size (noun), do you?'' YodaLib: A Demographic-Aware Humor Generation Framework](https://mlsanity.com/paper/2006.00578/) (2020)
- [Synopsis of the workshop on humor and cognition](https://mlsanity.com/paper/1310.1676/) (2013)

## Built on by (most cited first, 5 of 5)

- [Can Large Language Models Transform Computational Social Science?](https://mlsanity.com/paper/2305.03514/) (2023)
- [Let's Think Outside the Box: Exploring Leap-of-Thought in Large Language Models with Creative Humor Generation](https://mlsanity.com/paper/2312.02439/) (2023)
- [Innovative Thinking, Infinite Humor: Humor Research of Large Language Models through Structured Thought Leaps](https://mlsanity.com/paper/2410.10370/) (2024)
- [Towards High-Level Semantic Intelligence](https://mlsanity.com/paper/2607.24082/) (2026)
- [Cross-Model Humor Preference Modeling with Cards Against Humanity](https://mlsanity.com/paper/2608.07481/) (2026)

## Abstract (arXiv)

Humor is an inherently social phenomenon, with humorous utterances shaped by what is socially and culturally accepted. Understanding humor is an important NLP challenge, with many applications to human-computer interactions. In this work we explore humor in the context of Cards Against Humanity -- a party game where players complete fill-in-the-blank statements using cards that can be offensive or politically incorrect. We introduce a novel dataset of 300,000 online games of Cards Against Humanity, including 785K unique jokes, analyze it and provide insights. We trained machine learning models to predict the winning joke per game, achieving performance twice as good (20%) as random, even without any user information. On the more difficult task of judging novel cards, we see the models' ability to generalize is moderate. Interestingly, we find that our models are primarily focused on punchline card, with the context having little impact. Analyzing feature importance, we observe that short, crude, juvenile punchlines tend to win.